Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders.
Luke MarksAmir AbdullahLuna MendezRauno ArikePhilip H. S. TorrFazl BarezPublished in: CoRR (2023)
Keyphrases
- language model
- probabilistic model
- language modeling
- statistical language models
- language modelling
- relevance model
- document retrieval
- n gram
- retrieval model
- query expansion
- speech recognition
- smoothing methods
- language model for information retrieval
- information retrieval
- statistical language modeling
- translation model
- vector space model
- statistical models
- high dimensional
- document ranking
- ir models
- ad hoc information retrieval
- test collection